Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, openWorldHint=true and idempotentHint=false, and the description adds real context beyond them: paid-data consumption, a 10-minute per-workspace throttle, and idempotency-key retry semantics. The one material gap is what happens to the existing queue/dismissed opportunities on recompute — with destructiveHint=false an agent still cannot tell whether prior state is preserved or replaced.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler, and the information is front-loaded: what it recomputes first, then the cost/rate constraint, then the idempotency instruction. Every clause carries a distinct, actionable fact.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, and the description covers cost, throttle and retry behavior for this single-parameter tool. The remaining hole is the state-transition question (does recomputation replace or merge with existing opportunities, and what happens to dismissed ones) plus auth requirements, which for a write-flagged tool is a meaningful omission.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% (the idempotency_key property carries only min/max length), so the description must carry the meaning, and it does: a unique key per call, reused on retry. It does not restate the 8–200 character format constraint, but the key's purpose and lifecycle — the part an agent actually needs — are supplied.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('Recompute the workspace's opportunity queue') and explains the inputs it derives from ('tracked questions and AI citation data') plus the downstream effect ('look for new topics'). It is clearly distinguishable from the read-oriented siblings list_opportunities/list_questions in kind, but it never names or contrasts any sibling explicitly, so it stops just short of the top band.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives genuine operational guidance — the call consumes paid search/AI data and is limited to once per 10 minutes per workspace, and retries must reuse the same key. What it does not give is when to reach for this tool versus list_opportunities (read the current queue) or refresh_share_of_voice (a different recompute), leaving the selection decision to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.